ironxyz

ironxyz

Official MCP (Model Context Protocol) server for Iron.xyz API, designed to work with Claude Desktop, Cursor IDE and other MCP compatible clients.

Category
Visit Server

README

@ironxyz/mcp-server

Official MCP (Model Context Protocol) server for Iron.xyz API, designed to work with Claude Desktop, Cursor IDE and other MCP compatible clients.

Features

This MCP server provides three main tools for exploring and interacting with the Iron.xyz API:

  1. list-all-endpoints - Lists all API endpoints from the Iron.xyz OpenAPI specification in a concise format suitable for LLM consumption
  2. get-api-specs - Gets detailed OpenAPI specification for a specific endpoint
  3. invoke-api-endpoint - Actually calls the Iron.xyz API endpoints with proper authentication and validation

Quick Start

No installation required! Use with npx in your host:

Configuration

Add this to your MCP Host (Claude Desktop / Cursor IDE etc) configuration:

{
  "mcpServers": {
    "ironxyz": {
      "command": "npx",
      "args": ["-y", "@ironxyz/mcp-server"],
      "env": {
        "IRON_ENVIRONMENT": "production"
      }
    }
  }
}

Configuration Options

Configure the server using environment variables:

Variable Description Default Options
IRON_ENVIRONMENT Iron.xyz environment to use production production, sandbox
IRON_API_KEY Iron.xyz API key for authentication None Your API key from Iron.xyz dashboard
IRON_READ_ONLY_MODE Restrict to GET requests only false true, false
IRON_BASE_URL Custom base URL for API calls Auto-detected based on environment Any valid URL
IRON_OPENAPI_SPEC_URL Custom OpenAPI spec URL Auto-detected based on environment Any valid URL
IRON_LOCAL_SPEC_PATH Local fallback spec file path ./ironxyz-openapi-spec.yaml Any valid file path

Environment Examples

Production Environment (default):

{
  "env": {
    "IRON_ENVIRONMENT": "production"
  }
}

Sandbox Environment:

{
  "env": {
    "IRON_ENVIRONMENT": "sandbox"
  }
}

With API Key (for endpoint invocation):

{
  "env": {
    "IRON_ENVIRONMENT": "production",
    "IRON_API_KEY": "your-iron-api-key-here"
  }
}

Read-only mode (GET requests only):

{
  "env": {
    "IRON_ENVIRONMENT": "production",
    "IRON_API_KEY": "your-iron-api-key-here",
    "IRON_READ_ONLY_MODE": "true"
  }
}

Custom OpenAPI Spec URL:

{
  "env": {
    "IRON_ENVIRONMENT": "production",
    "IRON_OPENAPI_SPEC_URL": "https://your-custom-spec-url.com/spec"
  }
}

Development

Local Installation

  1. Install dependencies:

    pnpm install
    
  2. Build the project:

    pnpm run build
    

Running Locally

pnpm start

Or for development:

pnpm run dev

Tools Available

list-all-endpoints

Lists all API endpoints from the Iron.xyz OpenAPI specification.

Parameters:

  • filterByTag (string, optional): Filter endpoints by tag

Example usage:

{
  "tool": "list-all-endpoints",
  "arguments": {
    "filterByTag": "users"
  }
}

get-api-specs

Gets detailed OpenAPI specification for a specific endpoint.

Parameters:

  • path (string, required): The API path (e.g., '/v1/users')
  • method (string, required): The HTTP method (GET, POST, PUT, DELETE, etc.)

Example usage:

{
  "tool": "get-api-specs",
  "arguments": {
    "path": "/v1/users",
    "method": "GET"
  }
}

invoke-api-endpoint

Actually calls the Iron.xyz API endpoints with proper authentication and validation.

Parameters:

  • path (string, required): The API path (e.g., '/customers') - /api prefix is added automatically
  • method (string, required): The HTTP method (GET, POST, PUT, DELETE, etc.)
  • parameters (object, optional): Query parameters as key-value pairs
  • headers (object, optional): Additional headers as key-value pairs
  • body (object, optional): Request body for POST/PUT/PATCH requests

Features:

  • ✅ Authentication: Automatically adds API key if configured
  • ✅ Read-only mode: Optional restriction to GET requests only
  • ✅ Validation: Validates endpoints against OpenAPI specification
  • ✅ Error handling: Comprehensive error responses with details
  • ✅ Environment awareness: Works with both sandbox and production

Example usage:

{
  "tool": "invoke-api-endpoint",
  "arguments": {
    "path": "/customers",
    "method": "GET",
    "parameters": {
      "limit": 10,
      "offset": 0
    }
  }
}

Example with POST request:

{
  "tool": "invoke-api-endpoint",
  "arguments": {
    "path": "/customers",
    "method": "POST",
    "headers": {
      "IDEMPOTENCY-KEY": "123e4567-e89b-12d3-a456-426614174000"
    },
    "body": {
      "name": "John Doe",
      "email": "john@example.com",
      "type": "individual"
    }
  }
}

Error Handling

The server includes comprehensive error handling for:

  • Missing or invalid OpenAPI specification API
  • Invalid endpoint paths or methods
  • Network issues with external services
  • Malformed tool arguments

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured